In a previous work (Ognibene et al., 2008) we presented a reinforcement-learning neuro-robotic architecture, based on neural population codes, which was able to develop attention control policies by interacting with the environment based on a rewarded reaching task it had to accomplish. In this paper the same architecture is used to investigate the types of internal representations that this same architecture develops when exposed to two classes of environments where objects are organised on the basis of contrasting spatial relations (Figure 1).

Ognibene, D., Pezzulo, G., Baldassare, G. (2009). How Are Representations Affected by Scene Statistics in an Adaptive Active Vision System?. In Epirob 2009 (pp.360-365). Springer.

How Are Representations Affected by Scene Statistics in an Adaptive Active Vision System?

Ognibene D
Primo
;
2009

Abstract

In a previous work (Ognibene et al., 2008) we presented a reinforcement-learning neuro-robotic architecture, based on neural population codes, which was able to develop attention control policies by interacting with the environment based on a rewarded reaching task it had to accomplish. In this paper the same architecture is used to investigate the types of internal representations that this same architecture develops when exposed to two classes of environments where objects are organised on the basis of contrasting spatial relations (Figure 1).
paper
developmental trajectory; Artificial neural networks; reinforcement learning; active vision; active perception; sensory motor loop;
English
EPIROB 2009 12-14 NOVEMBER
2009
Epirob 2009
2009
2
360
365
open
Ognibene, D., Pezzulo, G., Baldassare, G. (2009). How Are Representations Affected by Scene Statistics in an Adaptive Active Vision System?. In Epirob 2009 (pp.360-365). Springer.
File in questo prodotto:
File Dimensione Formato  
2009-A2-014.pdf

accesso aperto

Tipologia di allegato: Submitted Version (Pre-print)
Dimensione 304.12 kB
Formato Adobe PDF
304.12 kB Adobe PDF Visualizza/Apri
2009-A2-014.pdf

accesso aperto

Tipologia di allegato: Submitted Version (Pre-print)
Dimensione 304.12 kB
Formato Adobe PDF
304.12 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/301933
Citazioni
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
Social impact